Triple

T18689549
Position Surface form Disambiguated ID Type / Status
Subject President Merkin Muffley E456954 entity
Predicate basedOnAuthor P2806 FINISHED
Object Peter George NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Peter George | Statement: [President Merkin Muffley, basedOnAuthor, Peter George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter George
Context triple: [President Merkin Muffley, basedOnAuthor, Peter George]
  • A. Peter George chosen
    Peter George was a Welsh novelist and screenwriter best known for his Cold War thriller "Red Alert," which served as the basis for Stanley Kubrick's film "Dr. Strangelove."
  • B. Howard Hyde Russell
    Howard Hyde Russell was an American lawyer, clergyman, and prominent temperance leader best known as the founder and early driving force behind the Anti-Saloon League.
  • C. Anthony George
    Anthony George was an American television actor best known for his roles in mid-20th-century soap operas and crime dramas.
  • D. Paul Geoffrey
    Paul Geoffrey was a British actor best known for his role as Perceval in the 1981 fantasy film "Excalibur."
  • E. George Ernest
    George Ernest was an American child actor active in the 1930s and 1940s, known for his roles in family and adventure films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8d391eb488190ac2e9abf5bf255e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e55b2fc2cc8190a4726526a714a5eb completed April 19, 2026, 10:46 p.m.
Created at: April 10, 2026, 11:49 a.m.